Data-Driven Abstractions for Robots With Stochastic Dynamics
IEEE Transactions on Robotics
This article describes the construction of stochastic, data-based discrete abstractions for uncertain random processes continuous in time and space. Motivated by the fact that modeling processes often introduce errors which interfere with the implementation of control strategies, here the abstraction process proceeds in reverse: the methodology does not abstract models; rather it models abstractions. Specifically, it first formalizes a template for a family of stochastic abstractions, and then fits the parameters of that template to match the dynamics of the underlying process and ground the abstraction. The article also shows how the parameter-fitting approach can be implemented based on a probabilistic model validation approach which draws from randomized algorithms, and results in a discrete abstract model which is approximately simulated by the actual process physics, at a desired confidence level. In this way, the models afford the implementation of symbolic control plans with probabilistic guarantees at a desired level of fidelity.
2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. This article was originally published in IEEE Transactions on Robotics. The version of record is available at: https://doi.org/10.1109/TRO.2021.3119209
Discrete abstractions, randomized algorithms, simulation relations, stochastic processes
H. G. Tanner and A. Stager, "Data-Driven Abstractions for Robots With Stochastic Dynamics," in IEEE Transactions on Robotics, doi: 10.1109/TRO.2021.3119209.